{"total":99,"rows":[{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712,"area":null},{"id":"2102.07623","title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","created":"2021-02-15","cited_by_count":571,"area":null},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486,"area":null},{"id":"2109.04404","title":"All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality","created":"2021-09-09","cited_by_count":156,"area":null},{"id":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156,"area":null},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"area":null},{"id":"2106.04690","title":"Handcrafted Backdoors in Deep Neural Networks","created":"2021-06-08","cited_by_count":63,"area":null},{"id":"2110.07483","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","created":"2021-10-14","cited_by_count":62,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2112.12089","title":"Reflash Dropout in Image Super-Resolution","created":"2021-12-22","cited_by_count":41,"area":null},{"id":"2410.02984","title":"Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient","created":"2024-10-03","cited_by_count":40,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2103.16886","title":"Neural Response Interpretation through the Lens of Critical Pathways","created":"2021-03-31","cited_by_count":32,"area":null},{"id":"2211.12491","title":"ModelDiff: A Framework for Comparing Learning Algorithms","created":"2022-11-22","cited_by_count":30,"area":null},{"id":"2310.13061","title":"To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets","created":"2023-10-19","cited_by_count":24,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2406.19087","title":"Dimensions underlying the representational alignment of deep neural networks with humans","created":"2024-06-27","cited_by_count":22,"area":null},{"id":"2502.07551","title":"Early Stopping Against Label Noise Without Validation Data","created":"2025-02-11","cited_by_count":21,"area":null},{"id":"2210.03277","title":"Rethinking Normalization Methods in Federated Learning","created":"2022-10-07","cited_by_count":19,"area":null},{"id":"2307.05471","title":"Scale Alone Does not Improve Mechanistic Interpretability in Vision Models","created":"2023-07-11","cited_by_count":18,"area":"mechinterp"},{"id":"2311.09466","title":"Soft Matching Distance: A metric on neural representations that captures single-neuron tuning","created":"2023-11-16","cited_by_count":18,"area":null},{"id":"2101.07985","title":"Network Pruning using Adaptive Exemplar Filters","created":"2021-01-20","cited_by_count":16,"area":null},{"id":"2105.12807","title":"XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data","created":"2021-05-26","cited_by_count":13,"area":null},{"id":"2302.07937","title":"The Expressive Power of Tuning Only the Normalization Layers","created":"2023-02-15","cited_by_count":13,"area":null},{"id":"2108.05312","title":"Towards Interpretable Deep Networks for Monocular Depth Estimation","created":"2021-08-11","cited_by_count":12,"area":null},{"id":"2411.05698","title":"Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification","created":"2024-11-08","cited_by_count":12,"area":null},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2103.06002","title":"Robustness to Pruning Predicts Generalization in Deep Neural Networks","created":"2021-03-10","cited_by_count":10,"area":null},{"id":"2110.08058","title":"Quantifying Local Specialization in Deep Neural Networks","created":"2021-10-13","cited_by_count":10,"area":null},{"id":"2310.11431","title":"Identifying Interpretable Visual Features in Artificial and Biological Neural Systems","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2409.19069","title":"Localizing Memorization in SSL Vision Encoders","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2211.09817","title":"On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning","created":"2022-11-17","cited_by_count":7,"area":"offlinerl"},{"id":"2212.04316","title":"Bio-Inspired, Task-Free Continual Learning through Activity Regularization","created":"2022-12-08","cited_by_count":7,"area":null},{"id":"2103.06733","title":"Intraclass clustering: an implicit learning ability that regularizes DNNs","created":"2021-03-11","cited_by_count":6,"area":null},{"id":"2103.09716","title":"Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2108.01335","title":"Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability","created":"2021-08-03","cited_by_count":6,"area":null},{"id":"2203.10502","title":"Adversarial Parameter Attack on Deep Neural Networks","created":"2022-03-20","cited_by_count":6,"area":null},{"id":"2105.12344","title":"Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services","created":"2021-05-26","cited_by_count":5,"area":null},{"id":"2211.03970","title":"On the Algorithmic Stability and Generalization of Adaptive Optimization Methods","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2305.17409","title":"On the special role of class-selective neurons in early training","created":"2023-05-27","cited_by_count":5,"area":null},{"id":"2310.10708","title":"Automated Natural Language Explanation of Deep Visual Neurons with Large Models","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2406.12516","title":"Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation","created":"2024-06-18","cited_by_count":5,"area":"safety"},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2508.21421","title":"Rethinking Layer-wise Model Merging through Chain of Merges","created":"2025-08-29","cited_by_count":5,"area":null},{"id":"2107.10199","title":"Distribution of Classification Margins: Are All Data Equal?","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2205.01493","title":"On the uncertainty principle of neural networks","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2206.10821","title":"Coupling Visual Semantics of Artificial Neural Networks and Human Brain Function via Synchronized Activations","created":"2022-06-22","cited_by_count":4,"area":null},{"id":"2402.10983","title":"Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks","created":"2024-02-16","cited_by_count":4,"area":null},{"id":"2508.15094","title":"Evaluating Sparse Autoencoders for Monosemantic Representation","created":"2025-08-20","cited_by_count":4,"area":"mechinterp"},{"id":"2106.00673","title":"Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks","created":"2021-06-01","cited_by_count":3,"area":null},{"id":"2201.06357","title":"Disentangled Latent Transformer for Interpretable Monocular Height Estimation","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2205.15146","title":"Batch Normalization Is Blind to the First and Second Derivatives of the Loss","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2209.14074","title":"Recipro-CAM: Fast gradient-free visual explanations for convolutional neural networks","created":"2022-09-28","cited_by_count":3,"area":null},{"id":"2305.03238","title":"Reduction of Class Activation Uncertainty with Background Information","created":"2023-05-05","cited_by_count":3,"area":null},{"id":"2305.14521","title":"Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2312.05337","title":"Artificial Neural Nets and the Representation of Human Concepts","created":"2023-12-08","cited_by_count":3,"area":null},{"id":"2104.00851","title":"Estimating the Generalization in Deep Neural Networks via Sparsity","created":"2021-04-02","cited_by_count":2,"area":null},{"id":"2307.12941","title":"On Privileged and Convergent Bases in Neural Network Representations","created":"2023-07-24","cited_by_count":2,"area":null},{"id":"2407.17834","title":"Towards the Spectral bias Alleviation by Normalizations in Coordinate Networks","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2512.15267","title":"Distillation-Guided Structural Transfer for Continual Learning Beyond Sparse Distributed Memory","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2603.01879","title":"Diagnosing Generalization Failures from Representational Geometry Markers","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2105.04354","title":"AFINet: Attentive Feature Integration Networks for Image Classification","created":"2021-05-10","cited_by_count":1,"area":null},{"id":"2110.09974","title":"UniFed: A Unified Framework for Federated Learning on Non-IID Image Features","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2110.14404","title":"Separating Content and Style for Unsupervised Image-to-Image Translation","created":"2021-10-27","cited_by_count":1,"area":null},{"id":"2211.00416","title":"Higher-order mutual information reveals synergistic sub-networks for multi-neuron importance","created":"2022-11-01","cited_by_count":1,"area":null},{"id":"2310.06221","title":"Detecting and Learning Out-of-Distribution Data in the Open world: Algorithm and Theory","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2406.10954","title":"Towards Efficient Target-Level Machine Unlearning Based on Essential Graph","created":"2024-06-16","cited_by_count":1,"area":"safety"},{"id":"2410.01588","title":"DynFrs: An Efficient Framework for Machine Unlearning in Random Forest","created":"2024-10-02","cited_by_count":1,"area":"safety"},{"id":"2411.00383","title":"Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization","created":"2024-11-01","cited_by_count":1,"area":"synth"},{"id":"2505.15013","title":"Convergence of Adam in Deep ReLU Networks via Directional Complexity and Kakeya Bounds","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.17936","title":"Understanding Gated Neurons in Transformers from Their Input-Output Functionality","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2512.15938","title":"SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks","created":"2025-12-17","cited_by_count":1,"area":"mechinterp"},{"id":"2609.02889","title":"Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2108.11054","title":"Understanding of Kernels in CNN Models by Suppressing Irrelevant Visual Features in Images","created":"2021-08-25","cited_by_count":0,"area":null},{"id":"2109.09060","title":"On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars","created":"2021-09-19","cited_by_count":0,"area":null},{"id":"2203.08174","title":"Towards understanding deep learning with the natural clustering prior","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2211.04367","title":"Much Easier Said Than Done: Falsifying the Causal Relevance of Linear Decoding Methods","created":"2022-11-08","cited_by_count":0,"area":null},{"id":"2311.07864","title":"Probing clustering in neural network representations","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2312.11772","title":"CAManim: Animating end-to-end network activation maps","created":"2023-12-19","cited_by_count":0,"area":null},{"id":"2409.09088","title":"Y-Drop: A Conductance based Dropout for fully connected layers","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2409.16865","title":"Linking in Style: Understanding learned features in deep learning models","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2410.02006","title":"An Architecture Built for Federated Learning: Addressing Data Heterogeneity through Adaptive Normalization-Free Feature Recalibration","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2410.14461","title":"The Propensity for Density in Feed-forward Models","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2412.17692","title":"FedTLU: Federated Learning with Targeted Layer Updates","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2501.00885","title":"Representation in large language models","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2506.11615","title":"Machine Unlearning for Robust DNNs: Attribution-Guided Partitioning and Neuron Pruning in Noisy Environments","created":"2025-06-13","cited_by_count":0,"area":"safety"},{"id":"2510.03265","title":"MindCraft: How Concept Trees Take Shape In Deep Models","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.16086","title":"FSRF: Factorization-guided Semantic Recovery for Incomplete Multimodal Sentiment Analysis","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2602.23826","title":"GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.24350","title":"Evidence of an Emergent \"Self\" in Continual Robot Learning","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.24953","title":"Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.10627","title":"Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2606.13236","title":"Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.25529","title":"Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.18576","title":"Beyond receptive fields: sequence-pooled normalization can supply most of a sequence labeler's context","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.05126","title":"Coarse-Graining Hidden Representations: Unsupervised Neuron Selection via Mapping Entropy","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.20217","title":"Explaining spatial information flow in short-term traffic forecasting models using a gated graph attention network","created":"2026-08-09","cited_by_count":0,"area":null}],"next_cursor":null}